News for hackers. Stuff that matters.
Re:An open letter to FB, Twitter, Instagram regarding algori... by mc32 on Wednesday December 12, 2018 @12:32PM (#18665821)
You know things are broken when after you buy things you begin to get ads for the very thing you just bought. Now, you could forgive one ad network not knowing, but when you get served up ads by the people who know (have a record of the transaction) you bought something, you know something’s not working the way it should, optimally.
Re:An open letter to FB, Twitter, Instagram regarding algori... by wesd on Wednesday December 12, 2018 @12:56PM (#18666048)
There was a thread about this about a month ago:

https://news.ycombinator.com/item?id=18535748

"This one is funny, and has a couple of obvious solutions that have been prevented due to internal politics. The short answer is that they have a couple of different recommender systems, all competing against each other internally for sales lift. One is purely based off of pageviews. When you get recommendations for something you already bought, many times it is because you looked at it, but they don't know nor care if you already bought it. In their words, it works really well and accounting for sales brings in a lot of needless complexity.

Another is based off of sales. They also don't care if you already bought it because according to them, it works well. I remember trying to point out to them that for some types of products (specifically consumable products) this would work really well, but durables not so much. They claimed otherwise, that although they couldn't explain it, it was entirely common for people to rebuy things like vacuum cleaners and TVs and kitchen knives. I did a tiny bit of research to show them why they thought that, and proved with a small segment (vacuum cleaners, I believe), that after you filter for returns and replacements, that the probability of sequentially buying two of the same vacuum cleaner was effectively zero. They asked me to do it for the rest of their products, but I didn't have limitless time to spend on helping another team, especially one with a PM who was a complete dick to me for having the audacity to make a suggestion that he hadn't thought of.

In all, I believe there are a dozen or so recommender services, each with their own widget. There are tons of people that think all of the recommenders have merits in some areas and drawbacks in others, and the customer would be better off if they merged concepts into a single recommender system. But they all compete for sales lift, they all think their system is better than the other systems, and they refuse to merge concepts or incorporate outside ideas because they all believe they are fundamentally superior to the other recommenders. Just a small anecdotal glimpse at the hilariously counterproductive internal politics at Amazon."

Re:An open letter to FB, Twitter, Instagram regarding algori... by pbhjpbhj on Wednesday December 12, 2018 @05:23PM (#18668250)
>after you filter for returns and replacements, that the probability of sequentially buying two of the same vacuum cleaner was effectively zero.

But aren't the returns segment significant? "I bought this vacuum cleaner, returned it because it didn't suck (!); oh and look, this advert said this one has the best suction."?

Also, it seems common amongst some sectors to rebuy: like parents might buy a coat, find it's good, rebuy for the other children. Landlords might update their properties, rebuying items that work well and are robust enough, etc..

?

Re:An open letter to FB, Twitter, Instagram regarding algori... by mc32 on Wednesday December 12, 2018 @05:36PM (#18668338)
As a different poster than Parent posted, people are not goldfish. In all those repeat purchase scenarios the buyers know what they bought and can buy again if they so choose (in the near future). If it's six months down the road, I can see maybe this would be useful.
Re:An open letter to FB, Twitter, Instagram regarding algori... by kkarakk on Thursday December 13, 2018 @01:10AM (#18670226)
>they all compete

this is amazon's answer when an employee asks about work culture. it's working for now but the wheels seem to be falling off as the months pass by

Re:An open letter to FB, Twitter, Instagram regarding algori... by macleginn on Wednesday December 12, 2018 @01:22PM (#18666293)
This works the same way in Spotify’s recommender system. It keeps recommending you records you not only have already listened to a couple of times, but also added to your library and even made available offline. This is so fixable.
Re:An open letter to FB, Twitter, Instagram regarding algori... by RandallBrown on Wednesday December 12, 2018 @01:37PM (#18666476)
Spotify has several ways of recommending new music.

Discover Weekly is a brand new playlist of new music that you haven't listened to before.

They have their Daily Mixes which seem to be based on music you listen to regularly, with a few new, but similar, things mixed in.

I have found that it generally recommends the same type of music, so I can feel a little stuck in a few genres, but they just gave me a playlist of new music that's outside the genres I normally listen to.

I've been very happy with Spotify and their music discovery is a reason I don't see myself switching to Apple Music or similar anytime soon.

Re:An open letter to FB, Twitter, Instagram regarding algori... by lenocinor on Wednesday December 12, 2018 @05:21PM (#18668234)
Note that I generally agree about Discover Weekly, but it can recommend (and occasionally has recommended, for me) music I have heard before. I suspect this might be due to another suspicion of mine, that Discover Weekly puts songs into the playlist that people you follow are listening to. I've seen this happen many times with Discover Weekly, but I can never know for sure if it's a coincidence or not.
Re:An open letter to FB, Twitter, Instagram regarding algori... by filesystemdude on Wednesday December 12, 2018 @02:39PM (#18667053)
This is a WONTFIX bug.

The ad networks don't care. They're just serving ads paid for by a bidder who very much has decided that you're the target audience. They win when the bidder keeps bidding for your attention.

The bidder, meanwhile, probably has some very good numbers delivered to them quarterly from their ad agency showing that there is a very strong correlation between how they are targeting their ads, and actual purchase intent, and low and behold, purchases! When the ad is delivered relative to your purchase is an afterthought, or perhaps, just not worth paying their adtech people to fix. (After all, adtech engineers are expensive, and whatever they're doing seems to be working, so why change?)

And, the agency who set up the campaign doesn't have any problem cashing the checks for their successful work.

I'm not saying it's not broken, I'm saying the incentive structure currently is not set up in a way that will ever change it.

Re:An open letter to FB, Twitter, Instagram regarding algori... by harryh on Wednesday December 12, 2018 @05:35PM (#18668334)
Nah, this is definitely not evidence of brokenness. People rebuy things they've bought recently all the time, certainly more often than the general population. Maybe they want a 2nd one. Maybe the 1st one broke. Maybe they liked it so much they want a 2nd one to give as a gift. All kinds of reasons.

patio11 has a great tweetstream on this issue.

https://twitter.com/patio11/status/982208307057246209

Re:An open letter to FB, Twitter, Instagram regarding algori... by mc32 on Wednesday December 12, 2018 @05:44PM (#18668392)
Most of these things are not things like candy or a latte. They're durable items I'm unlikely to buy in the near future. If I buy an 8oz hammer, don't recommend another 8oz hammer. I can see perhaps recommending nails, or maybe a ball-peen hammer, maybe a chisel or punch, but not the exact same item. If it's defective, I'll return and perh get an exchange.

Or I bought socks. "Oh, they must have forgotten they actually wanted 12 pairs, not 8". Ok, remind me in a few months, I might be ready to buy again, but not right after the purchase.

Re:An open letter to FB, Twitter, Instagram regarding algori... by harryh on Wednesday December 12, 2018 @06:31PM (#18668639)
Statistically speaking, a person who just bought an 8oz hammer is much more likely to buy another 8oz hammer than some other random person from the population of people who has never shown any interest in hammers at all.
Re:An open letter to FB, Twitter, Instagram regarding algori... by mc32 on Wednesday December 12, 2018 @06:42PM (#18668675)
Sure but I'm going to guess statistically they are more likely to buy something not a hammer than a hammer. Maybe "people who bought a hammer also bought...", or, you bought a hammer and nails, here is a cordless drill. I mean, why would I buy a hammer twice in a row, and after that unlikelihood, a third hammer?

If I were going to buy two hammers, I’d have put “2” in the basket in the first place. That’s the more likely scenario. I mean they are not operating blind in a vacuum. They know what I just bought. We’re not trying to guess against an unknown person with unknown purchasing history.

Re:An open letter to FB, Twitter, Instagram regarding algori... by tptacek on Thursday December 13, 2018 @12:11AM (#18669985)
If you're advertising hammers, and you can isolate a cohort of users statistically more likely to buy hammers than users at large, it would be irrational not to target hammer ads at those users.
Re:An open letter to FB, Twitter, Instagram regarding algori... by dingaling on Wednesday December 12, 2018 @12:47PM (#18665964)
I once heard that that is at least partially intentional in order to reassure the customer that it was a wise purchase. To prevent post-purchase regret and cancellation.
Re:An open letter to FB, Twitter, Instagram regarding algori... by Klathmon on Wednesday December 12, 2018 @12:45PM (#18665949)
But every ad network ive ever worked with already allows you to define categories of people you specifically don't want to show your ads to.

It's on the shopders of the ad creator to set that up though. I did read a comment one time that said the companies might be doing it on purpose, to "reaffirm" you made the right choice going with their product. Not sure how true that is, but it might factor in.

Re:An open letter to FB, Twitter, Instagram regarding algori... by mc32 on Wednesday December 12, 2018 @12:53PM (#18666028)
Honestly, it’s a turn off for me; or rather a small annoyance. But if true, it must work for most people if true, though I’m having a hard time imagining people not slightly annoyed at this ad behavior.
Re:An open letter to FB, Twitter, Instagram regarding algori... by Klathmon on Wednesday December 12, 2018 @01:04PM (#18666134)
Unfortunately being annoying and working aren't mutually exclusive.

And if that is really the case, then I'd argue it's on ad networks like Google and Facebook to find a way to realign incentives here so that what works best or makes the most money isn't annoying to the user (similar to how they are attempting to ban overly obnoxious ads).

Re:An open letter to FB, Twitter, Instagram regarding algori... by kapad on Friday December 14, 2018 @01:21AM (#18678843)
This happens all the time. And I don't understand the reason for it. Companies are incentivized to understand that I have already bought something and then NOT have to spend on advertising the same thing to me. Yet they do. No idea why.
Re:An open letter to FB, Twitter, Instagram regarding algori... by patmcguire on Wednesday December 12, 2018 @01:23PM (#18666303)
I see this sentiment a lot, but I think it probably does make financial sense to show you ads for a thing you already bought. There are often a few whales out there who are buying one of a thing to sample and then might later buy hundreds or thousands.
Re:An open letter to FB, Twitter, Instagram regarding algori... by jfk13 on Wednesday December 12, 2018 @01:30PM (#18666400)
If I were buying a sample of something, with a view to buying in bulk, I don't think I'd base that bulk-buying decision on ads that follow me around after the sample purchase. I've already found the product and bought a sample; any decision to buy a thousand of them will be based on my evaluation of that sample. I'm not likely to forget about the whole project until reminded by an ad that stalks me around the web...
Re:An open letter to FB, Twitter, Instagram regarding algori... by patmcguire on Wednesday December 12, 2018 @07:28PM (#18668901)
Doesn't matter how low is if the payout is high enough. Also, it's not like they've got any better ad to show you, CTR is something like one in a thousand for display.
Re:An open letter to FB, Twitter, Instagram regarding algori... by theNJR on Wednesday December 12, 2018 @01:42PM (#18666521)
Remarketing converts multiple times higher than prospecting.

For everyone 1 person annoyed by seeing an ad for a product they bought, 10 others buy.